Lead/Senior Agentic AI Systems Engineer

We are looking for an Agentic AI System Engineer to design and optimize LLM-powered development workflows and autonomous agent systems. The role includes building advanced reasoning frameworks, RAG pipelines, and multi-agent architectures to support large-scale code modernization and contextualization. You will work on improving system performance through prompt engineering, caching strategies, and latency optimization. The position also involves integrating cutting-edge AI coding tools into secure, scalable production environments aligned with enterprise privacy and CI/CD standards. Experience with AI orchestration, distributed systems, and developer tooling is highly valued. 1.Lead Agentic AI Systems Engineer (7+ years) Roles and Responsibilities: Provide technical leadership and mentorship for RAG and agent development, establishing a clear technological vision for the team. Continuously evaluate and benchmark AI-assisted coding tools, repository-level engineering platforms, and software automation models to generate actionable cost/benefit analyses. Architect high-efficiency RAG structures and autonomous (agentic) workflows tailored specifically for the modernization and conversion of massive codebases. Assess the specific code-conversion and automation needs of internal and external teams, delivering strategic technical roadmaps and expert guidance. Define enterprise-wide token optimization strategies and ensure all AI systems strictly comply with on-prem/cloud network, data privacy, and information security standards. What You Will Need: Ability to translate complex business problems into scalable, maintainable technical architectures. Deep expertise in LLM-based systems, prompt engineering, and agent orchestration frameworks, supported by a strong foundation in probabilistic reasoning and multi-component system design. Capability to architect, design, and implement agent runtimes and orchestration platforms that drive AI-assisted development workflows. A proven track record of designing, building, and evolving multi-agent AI systems from initial concept through to production. Leadership skills to drive technical planning, architectural discussions, and cross-team decision-making while elevating overall engineering standards. Strong collaborative skills to work effectively with business stakeholders, product owners, and vertical leaders. A pragmatic, outcome-driven approach to navigating ambiguity and rapidly evolving technologies. What They're Looking For: Experience: 7+ years of industry-relevant engineering experience. AI Systems Mastery: Proven expertise in building and deploying AI architectures that utilize reasoning tools, multi-agent frameworks, and RAG/tool-augmented workflows, with an emphasis on system-level reliability and robust decision aggregation. AI Technology Stack: Deep architectural knowledge and hands-on experience with: Coding Systems & Agents: Devin, Cursor, GitHub Copilot, CodeArts Agent, Antigravity, Codeium. Code-Specific Models: DeepSeek-Coder, StarCoder, OpenAI Codex (and successors), Code Llama, Qwen-Coder. Foundational Models: Claude (Sonnet/Opus), GPT-4o, Gemini Pro. Platform Design: Expertise in cloud-native architecture, scalable platform design, and integrating AI systems with enterprise operational data. Infrastructure & Tooling: Experience operating developer platforms (SDKs, CLIs, APIs, runtimes) and deploying end-to-end AI Agent/RAG solutions at scale. Programming & Ecosystems: Strong proficiency in at least one major programming language (e.g., Kotlin, SwiftUI, ArkTS, Java, Python, C++), specifically encompassing mobile ecosystems (Android, iOS, HarmonyOS), with practical experience integrating AI/ML into developer workflows. Education: Bachelor’s degree in Computer Science, Engineering, or a related technical field (Advanced degree preferred). Optional / Nice-to-Have: Professional cloud certifications (Azure, AWS, or GCP). Architecture-level expertise in Kubernetes and CI/CD pipelines 2.Agentic AI Systems Engineer (4+ years) Roles and Responsibilities: Design and deploy agentic AI systems that utilize multi-step reasoning, tool integration, and multi-agent coordination to resolve complex tasks via structured decision-making. Build advanced RAG infrastructures for deep semantic analysis of codebases, actively constructing end-to-end AI-assisted code conversion pipelines. Program intelligent, autonomous agent workflows capable of executing code analysis, transformation, test generation, and debugging utilizing specialized coding extensions, APIs, and terminal-based tools. What You Will Need: Ability to ensure all deployed AI solutions are highly resilient, observable, and production-ready. Capability to manage prompt engineering, context windows, and model orchestration end-to-end using dedicated code-generation LLMs. Skills to optimize AI services for maximum performance, minimal cost, and robust security. Competence in securely and scalably deploying AI services within cloud environments. A hands-on approach to implementing AI projects alongside broader technical engineering teams. Aptitude for preparing comprehensive technical documentation and architectural diagrams for AI solutions. What They're Looking For: Experience: 4+ years of industry-relevant engineering experience. AI Systems Development: Expertise in building reasoning tools, multi-agent architectures, and RAG/tool-augmented workflows with a focus on output aggregation and system reliability. Pipeline Engineering: Experience constructing scalable, end-to-end AI pipelines, carefully balancing cost, latency, and observability. AI Technology Stack: Practical implementation experience and familiarity with: Coding Systems & Agents: Devin, Cursor, GitHub Copilot, CodeArts Agent, Antigravity, Codeium. Code-Specific Models: DeepSeek-Coder, StarCoder, OpenAI Codex (and successors), Code Llama, Qwen-Coder. Foundational Models: Claude (Sonnet/Opus), GPT-4o, Gemini Pro. Optimization Skills: Deep understanding of tuning code-generation models, including LLM evaluation, code-specific prompting, and performance/cost optimization. Programming & Ecosystems: Strong proficiency in at least one major programming language (e.g., Kotlin, SwiftUI, ArkTS, Java, Python, C++), encompassing mobile ecosystems (Android, iOS, HarmonyOS), with hands-on AI/ML integration experience. Education: Bachelor’s degree in Computer Science, Engineering, or a related technical field. Optional / Nice-to-Have: Hands-on experience with AI benchmarking and prompt optimization using code-centric datasets (e.g., HumanEval, SWE-bench). Familiarity with GPU workloads and inference serving. Practical knowledge of Kubernetes and CI/CD processes.